Towards Understanding People's Experiences of AI Computer Vision Fitness Instructor Apps

The recent rise in on-device AI computer vision and dialogue systems has facilitated a growing number of AI fitness related instructional apps. However, these technologies have yet to be explored within the HCI community. To investigate this domain we recruited 12 participants and asked them to engage with five recently launched AI fitness instructor apps. We interviewed participants and thematically analysed transcripts to understand their experience and expectations of these technologies. Our qualitative analysis outlines five main themes focusing on; limitations of computer vision, visual feedback, dialogue with the AI, adapting to the user, and working out with the instructor. Based upon our findings we present five design considerations for designers that relate to three key areas: feedback and motivation, personalising the experience, and building a relationship with the AI. We contribute a first look into people's initial experiences with on-device AI fitness instructor applications and we provide design considerations to guide future contextually-aware AI research in this domain.